about · email me · subscribe
Spurious correlation #4,057 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in New York City and the second variable is Arson in United States.  The chart goes from 1985 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the smog lifted in NYC, the arsonists found it harder to *fuel* their fiery shenanigans. With cleaner air, there was less *combustion* temptation, leading to a nationwide decrease in arson. It seems like a case of *smoke* and mirrors, but perhaps fresher air truly does dampen the flames of mischief!

Model: dalle-3
Prompt: Generate an image of a steampunk-inspired New York City skyline at sunset, with warm lighting casting a golden glow on the buildings. In the foreground, a group of steampunk-themed arsonists are shown, surrounded by the bustling city, but the absence of thick smoke creates a challenge for them to start a fire. The scene should capture the feeling of a cooling-off period for the crime, with a sense of retro-futuristic steampunk elements integrated into the cityscape. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Air pollution in New York City and Arson in United States. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Futuristic Cute cartoon Steampunk Magic realism 3D Pixar Style
ChatGPT: Steampunk

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air pollution in New York City and Arson in United States, in the following situation: As air pollution decreased in NYC, there was less smoke to "fuel" arsonists' desires, leading to a "burnout" in arson cases across the US. With cleaner air, arsonists found it harder to "ignite" their passion for fire-starting, leading to a "cooling off" period for the crime.. Keep the description simple.
ChatGPT: In New York City, the sun sets over the skyline, casting a warm glow on the city buildings as the air pollution decreases. The skyline is clear and the air feels cool and fresh. In the distance, a group of arsonists stand amidst the bustling city, but the absence of thick smoke in the air makes it difficult for them to start a fire. As a result, the number of arson cases across the United States begins to dwindle, symbolizing a "cooling off" period for the crime.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ Steampunk ] and depicting this scene: In New York City, the sun sets over the skyline, casting a warm glow on the city buildings as the air pollution decreases. The skyline is clear and the air feels cool and fresh. In the distance, a group of arsonists stand amidst the bustling city, but the absence of thick smoke in the air makes it difficult for them to start a fire. As a result, the number of arson cases across the United States begins to dwindle, symbolizing a "cooling off" period for the crime. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a steampunk-inspired New York City skyline at sunset, with warm lighting casting a golden glow on the buildings. In the foreground, a group of steampunk-themed arsonists are shown, surrounded by the bustling city, but the absence of thick smoke creates a challenge for them to start a fire. The scene should capture the feeling of a cooling-off period for the crime, with a sense of retro-futuristic steampunk elements integrated into the cityscape.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Air pollution in New York City caused Arson in United States to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)
The Dirty Air Beware: A Flare for Arson in the Big Apple

The Journal of Urban Fire Ecology

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air pollution in New York City and Arson in United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Rhyme words in the title.

Your research team used data from Environmental Protection Agency and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.8958566 and p < 0.01 for 1985 to 2022.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The Dirty Air Beware: A Flare for Arson in the Big Apple

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in New York City and the incidence of arson across the United States. The findings reveal a strikingly strong correlation between the two, raising eyebrows and flames alike. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our research team discovered a correlation coefficient of 0.8958566 and p < 0.01 for the period spanning 1985 to 2022. This suggests that as the air quality in the bustling urban metropolis deteriorates, so too does the propensity for fiery mischief across the nation. But don't worry, we won't let the pressure burn us out—after all, we'd much prefer to ignite curiosity rather than fires.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between Air pollution in New York City and Arson in United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
The Dirty Air Beware: A Flare for Arson in the Big Apple

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in New York City and the incidence of arson across the United States. The findings reveal a strikingly strong correlation between the two, raising eyebrows and flames alike. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our research team discovered a correlation coefficient of 0.8958566 and p < 0.01 for the period spanning 1985 to 2022. This suggests that as the air quality in the bustling urban metropolis deteriorates, so too does the propensity for fiery mischief across the nation. But don't worry, we won't let the pressure burn us out—after all, we'd much prefer to ignite curiosity rather than fires.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Fire! The word itself carries both a sense of danger and a smoky aroma of intrigue. Amidst this dichotomy, the link between air pollution and arson has remained elusive, much like a firefly in a foggy night. However, recent research has shed light on the potential relationship between the quality of the air we breathe and the propensity for an unexpected dance of flames.

As we dive into this scorching topic, let's not be too hasty, as excessive speed in research can lead to "inflammation" of the results – and I don't mean that in a good way! What do you call an alligator in a vest? An investigator! But I digress. Our study aims to provide a thorough investigation into the connection between air pollution in New York City and the occurrence of arson incidents across the United States.

The need to understand the intersection of these factors has become burningly clear, especially in light of the devastating impacts of both air pollution and arson on public health and safety. And speaking of burning, did you hear about the fire at the circus? It was in tents!

Our research takes a meticulous approach, drawing upon years of data collected by the Environmental Protection Agency and the FBI Criminal Justice Information Services. This data, spanning from 1985 to 2022, allowed us to analyze the patterns and correlations that may ignite a deeper understanding of the potential influence of urban air quality on nationwide arson incidents.

Now, as we embark on this fiery journey of exploration, let's remember the importance of maintaining a clear perspective—after all, polluted air can certainly cloud our judgment, and we wouldn't want to jump to any hasty conclusions. Why did the air pollution researcher break up with the atmospheric scientist? Because there was just too much smog between them!

Stay on the edge on your seats as we unravel the compelling findings that may leave you both astounded and fired up!


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in New York City and Arson in United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
The Dirty Air Beware: A Flare for Arson in the Big Apple

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in New York City and the incidence of arson across the United States. The findings reveal a strikingly strong correlation between the two, raising eyebrows and flames alike. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our research team discovered a correlation coefficient of 0.8958566 and p < 0.01 for the period spanning 1985 to 2022. This suggests that as the air quality in the bustling urban metropolis deteriorates, so too does the propensity for fiery mischief across the nation. But don't worry, we won't let the pressure burn us out—after all, we'd much prefer to ignite curiosity rather than fires.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Fire! The word itself carries both a sense of danger and a smoky aroma of intrigue. Amidst this dichotomy, the link between air pollution and arson has remained elusive, much like a firefly in a foggy night. However, recent research has shed light on the potential relationship between the quality of the air we breathe and the propensity for an unexpected dance of flames.
As we dive into this scorching topic, let's not be too hasty, as excessive speed in research can lead to "inflammation" of the results – and I don't mean that in a good way! What do you call an alligator in a vest? An investigator! But I digress. Our study aims to provide a thorough investigation into the connection between air pollution in New York City and the occurrence of arson incidents across the United States.
The need to understand the intersection of these factors has become burningly clear, especially in light of the devastating impacts of both air pollution and arson on public health and safety. And speaking of burning, did you hear about the fire at the circus? It was in tents!
Our research takes a meticulous approach, drawing upon years of data collected by the Environmental Protection Agency and the FBI Criminal Justice Information Services. This data, spanning from 1985 to 2022, allowed us to analyze the patterns and correlations that may ignite a deeper understanding of the potential influence of urban air quality on nationwide arson incidents.
Now, as we embark on this fiery journey of exploration, let's remember the importance of maintaining a clear perspective—after all, polluted air can certainly cloud our judgment, and we wouldn't want to jump to any hasty conclusions. Why did the air pollution researcher break up with the atmospheric scientist? Because there was just too much smog between them!
Stay on the edge on your seats as we unravel the compelling findings that may leave you both astounded and fired up!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The link between air pollution and arson has been a topic of interest for researchers for decades. In "Smith et al.," the authors find that air pollution levels in urban areas are associated with various detrimental health outcomes, ranging from respiratory diseases to cardiovascular distress. Similarly, in "Doe and Jones," the authors report on the societal and economic impacts of arson incidents, highlighting the need for further exploration into the factors that may contribute to such criminal behavior.

But enough with the serious talk - let's lighten the mood with a relevant dad joke. Did you hear about the fire at the shoe factory? Thousands of soles were lost, but the employees managed to escape. Now, back to the literature.

In "Breathless Cities" by Jane Smith, the book examines the complex interplay between air pollution and urban life, delving into the insidious effects of polluted air on both the environment and human health. Similarly, "Toxic Tales" by John Doe offers a captivating exploration of the hazardous consequences of environmental pollution, painting a vivid portrait of the struggles faced by communities grappling with toxic air quality.

On the fictional front, "Smoke Signals" by Sarah Jones presents a gripping narrative that intertwines the mysteries of arson with the atmospheric charm of a bustling city, drawing readers into a world where the smoky haze of intrigue hangs heavy in the air. In a similar vein, "Burning Bridges" by Jack Smith weaves a web of fiery drama and suspense, exploring the fiery consequences that arise when relationships go up in smoke.

As we transition to more unconventional sources, let's not overlook the valuable insights that can be gleaned from unexpected corners. Who would've thought that "Smokey the Bear" and "Captain Planet" could offer illuminating perspectives on the intersection of air pollution and fire-related incidents? While their adventures may be more fantastical than factual, the whimsical wisdom they impart is not to be underestimated.

Now, before we delve into the empirical findings, I feel compelled to share another dad joke. What did the firefighter name his twin sons? Jose and Hose-B! Ah, the sweet relief of a good pun amidst scholarly pursuits. But I promise, we will ignite the flames of knowledge with the earnestness they deserve.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in New York City and Arson in United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and FBI Criminal Justice Information Services . You used data from 1985 to 2022

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The Dirty Air Beware: A Flare for Arson in the Big Apple

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in New York City and the incidence of arson across the United States. The findings reveal a strikingly strong correlation between the two, raising eyebrows and flames alike. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our research team discovered a correlation coefficient of 0.8958566 and p < 0.01 for the period spanning 1985 to 2022. This suggests that as the air quality in the bustling urban metropolis deteriorates, so too does the propensity for fiery mischief across the nation. But don't worry, we won't let the pressure burn us out—after all, we'd much prefer to ignite curiosity rather than fires.

[[INTRODUCTION]]
Fire! The word itself carries both a sense of danger and a smoky aroma of intrigue. Amidst this dichotomy, the link between air pollution and arson has remained elusive, much like a firefly in a foggy night. However, recent research has shed light on the potential relationship between the quality of the air we breathe and the propensity for an unexpected dance of flames.
As we dive into this scorching topic, let's not be too hasty, as excessive speed in research can lead to "inflammation" of the results – and I don't mean that in a good way! What do you call an alligator in a vest? An investigator! But I digress. Our study aims to provide a thorough investigation into the connection between air pollution in New York City and the occurrence of arson incidents across the United States.
The need to understand the intersection of these factors has become burningly clear, especially in light of the devastating impacts of both air pollution and arson on public health and safety. And speaking of burning, did you hear about the fire at the circus? It was in tents!
Our research takes a meticulous approach, drawing upon years of data collected by the Environmental Protection Agency and the FBI Criminal Justice Information Services. This data, spanning from 1985 to 2022, allowed us to analyze the patterns and correlations that may ignite a deeper understanding of the potential influence of urban air quality on nationwide arson incidents.
Now, as we embark on this fiery journey of exploration, let's remember the importance of maintaining a clear perspective—after all, polluted air can certainly cloud our judgment, and we wouldn't want to jump to any hasty conclusions. Why did the air pollution researcher break up with the atmospheric scientist? Because there was just too much smog between them!
Stay on the edge on your seats as we unravel the compelling findings that may leave you both astounded and fired up!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the potentially fiery relationship between air pollution in New York City and the frequency of arson incidents across the United States, our research team employed a multidimensional approach akin to untangling a knot of firehoses. We first gathered air quality data from the Environmental Protection Agency, scrutinizing an abundance of metrics including particulate matter, ozone, carbon monoxide, sulfur dioxide, nitrogen dioxide, and volatile organic compounds. These data points were scrutinized with the precision of a seasoned detective sifting through evidence at a crime scene, seeking to discern any smoky patterns.

Simultaneously, we delved into the vaults of FBI Criminal Justice Information Services to procure comprehensive records of arson incidents from 1985 to 2022. The meticulous categorization of arson cases by city, temporal progression, and severity allowed us to construct a robust framework for analyzing the correlation with air pollution levels. We also extinguished any doubt regarding the quality and standardization of the data by cross-referencing it with other reliable sources to ensure our findings were anything but half-baked.

Furthermore, to add depth to our investigation, we utilized advanced statistical models, including multiple regression analysis and time series modeling, to model the temporal and spatial dynamics between the two variables with a precociousness comparable to a young firebrand.

We also accounted for various potential confounding factors, such as socioeconomic indicators and climatic conditions, to prevent any premature combustion of conclusions. This not only facilitated a more nuanced examination of the relationship but also allowed us to quench any doubts about the robustness of our findings, ensuring that our conclusions weren’t just smoke and mirrors.

Additionally, to confirm the stability and reliability of our analysis, we performed sensitivity analyses and utilized robustness checks, ensuring that our results didn’t go up in smoke at the slightest provocation.

In light of the complex and multifaceted nature of our investigation, we acknowledge that it demanded a level of meticulous attention usually reserved for defusing a bomb, but we remained undaunted, ensuring that our analytical approach was as precise as the aim of a skilled firefighter with a hose.

Overall, our methodology was a testament to the adage that reaching enlightening conclusions is akin to kindling a flame – it requires patience, precision, and the occasional humorous aside to keep the spirits high.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Air pollution in New York City and Arson in United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and FBI Criminal Justice Information Services .

For the time period 1985 to 2022, you found a correlation 0.8958566, r-squared of 0.8025591, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The Dirty Air Beware: A Flare for Arson in the Big Apple

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in New York City and the incidence of arson across the United States. The findings reveal a strikingly strong correlation between the two, raising eyebrows and flames alike. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our research team discovered a correlation coefficient of 0.8958566 and p < 0.01 for the period spanning 1985 to 2022. This suggests that as the air quality in the bustling urban metropolis deteriorates, so too does the propensity for fiery mischief across the nation. But don't worry, we won't let the pressure burn us out—after all, we'd much prefer to ignite curiosity rather than fires.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Fire! The word itself carries both a sense of danger and a smoky aroma of intrigue. Amidst this dichotomy, the link between air pollution and arson has remained elusive, much like a firefly in a foggy night. However, recent research has shed light on the potential relationship between the quality of the air we breathe and the propensity for an unexpected dance of flames.
As we dive into this scorching topic, let's not be too hasty, as excessive speed in research can lead to "inflammation" of the results – and I don't mean that in a good way! What do you call an alligator in a vest? An investigator! But I digress. Our study aims to provide a thorough investigation into the connection between air pollution in New York City and the occurrence of arson incidents across the United States.
The need to understand the intersection of these factors has become burningly clear, especially in light of the devastating impacts of both air pollution and arson on public health and safety. And speaking of burning, did you hear about the fire at the circus? It was in tents!
Our research takes a meticulous approach, drawing upon years of data collected by the Environmental Protection Agency and the FBI Criminal Justice Information Services. This data, spanning from 1985 to 2022, allowed us to analyze the patterns and correlations that may ignite a deeper understanding of the potential influence of urban air quality on nationwide arson incidents.
Now, as we embark on this fiery journey of exploration, let's remember the importance of maintaining a clear perspective—after all, polluted air can certainly cloud our judgment, and we wouldn't want to jump to any hasty conclusions. Why did the air pollution researcher break up with the atmospheric scientist? Because there was just too much smog between them!
Stay on the edge on your seats as we unravel the compelling findings that may leave you both astounded and fired up!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis revealed a remarkably strong correlation between air pollution levels in New York City and the incidence of arson across the United States. Our research team found a correlation coefficient of 0.8958566, an r-squared value of 0.8025591, and a p-value of less than 0.01. This statistically significant relationship suggests that as air quality in New York City worsens, there is a notable increase in the occurrence of arson incidents nationwide. It's almost as if the polluted air is fanning the flames of criminal activity across the country. Speaking of fanning flames, did you hear about the firefighter who was a great gardener? He really knew how to handle a hose!

The correlation is evident in the scatterplot depicted in Figure 1, which visually illustrates the robust relationship between air pollution levels in New York City and the incidence of arson across the United States. The plot shows a clear upward trend, reinforcing the strength of the association we uncovered. It's as clear as smoke billowing from a chimney on a cold winter's day.

These findings have significant implications for public policy and urban planning efforts, highlighting the need for targeted interventions to mitigate air pollution and address its potential role in fueling arson incidents. As we move forward, it's essential to keep in mind that a breath of fresh air might be just what we need to douse the flames of criminal mischief. After all, who knew that a breath of fresh air could be so crucial in crime prevention? Keep on breathing easy, folks!


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in New York City and Arson in United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
The Dirty Air Beware: A Flare for Arson in the Big Apple

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in New York City and the incidence of arson across the United States. The findings reveal a strikingly strong correlation between the two, raising eyebrows and flames alike. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our research team discovered a correlation coefficient of 0.8958566 and p < 0.01 for the period spanning 1985 to 2022. This suggests that as the air quality in the bustling urban metropolis deteriorates, so too does the propensity for fiery mischief across the nation. But don't worry, we won't let the pressure burn us out—after all, we'd much prefer to ignite curiosity rather than fires.

[[LITERATURE REVIEW]]
The link between air pollution and arson has been a topic of interest for researchers for decades. In "Smith et al.," the authors find that air pollution levels in urban areas are associated with various detrimental health outcomes, ranging from respiratory diseases to cardiovascular distress. Similarly, in "Doe and Jones," the authors report on the societal and economic impacts of arson incidents, highlighting the need for further exploration into the factors that may contribute to such criminal behavior.
But enough with the serious talk - let's lighten the mood with a relevant dad joke. Did you hear about the fire at the shoe factory? Thousands of soles were lost, but the employees managed to escape. Now, back to the literature.
In "Breathless Cities" by Jane Smith, the book examines the complex interplay between air pollution and urban life, delving into the insidious effects of polluted air on both the environment and human health. Similarly, "Toxic Tales" by John Doe offers a captivating exploration of the hazardous consequences of environmental pollution, painting a vivid portrait of the struggles faced by communities grappling with toxic air quality.
On the fictional front, "Smoke Signals" by Sarah Jones presents a gripping narrative that intertwines the mysteries of arson with the atmospheric charm of a bustling city, drawing readers into a world where the smoky haze of intrigue hangs heavy in the air. In a similar vein, "Burning Bridges" by Jack Smith weaves a web of fiery drama and suspense, exploring the fiery consequences that arise when relationships go up in smoke.
As we transition to more unconventional sources, let's not overlook the valuable insights that can be gleaned from unexpected corners. Who would've thought that "Smokey the Bear" and "Captain Planet" could offer illuminating perspectives on the intersection of air pollution and fire-related incidents? While their adventures may be more fantastical than factual, the whimsical wisdom they impart is not to be underestimated.
Now, before we delve into the empirical findings, I feel compelled to share another dad joke. What did the firefighter name his twin sons? Jose and Hose-B! Ah, the sweet relief of a good pun amidst scholarly pursuits. But I promise, we will ignite the flames of knowledge with the earnestness they deserve.

[[RESULTS]]
The results of our analysis revealed a remarkably strong correlation between air pollution levels in New York City and the incidence of arson across the United States. Our research team found a correlation coefficient of 0.8958566, an r-squared value of 0.8025591, and a p-value of less than 0.01. This statistically significant relationship suggests that as air quality in New York City worsens, there is a notable increase in the occurrence of arson incidents nationwide. It's almost as if the polluted air is fanning the flames of criminal activity across the country. Speaking of fanning flames, did you hear about the firefighter who was a great gardener? He really knew how to handle a hose!
The correlation is evident in the scatterplot depicted in Figure 1, which visually illustrates the robust relationship between air pollution levels in New York City and the incidence of arson across the United States. The plot shows a clear upward trend, reinforcing the strength of the association we uncovered. It's as clear as smoke billowing from a chimney on a cold winter's day.
These findings have significant implications for public policy and urban planning efforts, highlighting the need for targeted interventions to mitigate air pollution and address its potential role in fueling arson incidents. As we move forward, it's essential to keep in mind that a breath of fresh air might be just what we need to douse the flames of criminal mischief. After all, who knew that a breath of fresh air could be so crucial in crime prevention? Keep on breathing easy, folks!

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our study has shed light on the intriguing relationship between air pollution in New York City and the occurrence of arson across the United States. The findings not only corroborate previous research on the detrimental effects of air pollution on human health and societal well-being but also offer a unique perspective on its potential influence on criminal behavior. It appears that when it comes to the connection between polluted air and arson, the evidence is as clear as day—well, or rather, as clear as a smoggy day in the city.

Our results support the existing body of literature that has identified air pollution as a significant public health concern. As the air quality in New York City deteriorates, the chain of events that culminate in increased arson incidents across the nation becomes increasingly apparent. It seems that our research found itself caught in the crosshairs of pollution and pyromania. But fear not, we kept both feet firmly planted in the realm of scientific inquiry, ensuring that our findings sparkle brighter than a Fourth of July firework.

The strong correlation coefficient and statistically significant p-value in our analysis underscore the robustness of the relationship between air pollution levels in New York City and the incidence of arson nationwide. These findings not only validate the theories put forth by scholars and experts in the field but also add a fiery twist to the ongoing discourse on the multifaceted impacts of air pollution. It's as if the pollution was playing the role of an enthusiastic arsonist, igniting conversations not just about health and well-being but also about law and order.

It's important to recognize that while our study presents compelling evidence of a connection between air pollution and arson, there are layers of complexity that merit further investigation. One might say we're just scratching the surface, much like the flint of a matchstick before it ignites a blaze. Understanding the nuanced interplay between environmental factors and criminal behavior demands thoughtful consideration and interdisciplinary collaboration, ensuring that our grasp of the situation remains as steady as a seasoned firefighter wielding a powerful hose.

In conclusion, our research serves as a beacon of insight into the potential link between air pollution in New York City and the incidence of arson across the United States. The implications of our findings extend far beyond the realms of atmospheric science and criminology, offering a compelling reflection of the interconnectedness of urban dynamics and criminal activity. As we extinguish this discussion—pun intended—we invite further exploration into this fiery phenomenon, with the hope of illuminating the path toward cleaner, safer, and less flammable urban environments. After all, it's only natural to aspire to clear skies and fire-free horizons.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in New York City and Arson in United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Dirty Air Beware: A Flare for Arson in the Big Apple

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in New York City and the incidence of arson across the United States. The findings reveal a strikingly strong correlation between the two, raising eyebrows and flames alike. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our research team discovered a correlation coefficient of 0.8958566 and p < 0.01 for the period spanning 1985 to 2022. This suggests that as the air quality in the bustling urban metropolis deteriorates, so too does the propensity for fiery mischief across the nation. But don't worry, we won't let the pressure burn us out—after all, we'd much prefer to ignite curiosity rather than fires.

[[INTRDUCTION]]
Fire! The word itself carries both a sense of danger and a smoky aroma of intrigue. Amidst this dichotomy, the link between air pollution and arson has remained elusive, much like a firefly in a foggy night. However, recent research has shed light on the potential relationship between the quality of the air we breathe and the propensity for an unexpected dance of flames.
As we dive into this scorching topic, let's not be too hasty, as excessive speed in research can lead to "inflammation" of the results – and I don't mean that in a good way! What do you call an alligator in a vest? An investigator! But I digress. Our study aims to provide a thorough investigation into the connection between air pollution in New York City and the occurrence of arson incidents across the United States.
The need to understand the intersection of these factors has become burningly clear, especially in light of the devastating impacts of both air pollution and arson on public health and safety. And speaking of burning, did you hear about the fire at the circus? It was in tents!
Our research takes a meticulous approach, drawing upon years of data collected by the Environmental Protection Agency and the FBI Criminal Justice Information Services. This data, spanning from 1985 to 2022, allowed us to analyze the patterns and correlations that may ignite a deeper understanding of the potential influence of urban air quality on nationwide arson incidents.
Now, as we embark on this fiery journey of exploration, let's remember the importance of maintaining a clear perspective—after all, polluted air can certainly cloud our judgment, and we wouldn't want to jump to any hasty conclusions. Why did the air pollution researcher break up with the atmospheric scientist? Because there was just too much smog between them!
Stay on the edge on your seats as we unravel the compelling findings that may leave you both astounded and fired up!

[[RESULTS]]
The results of our analysis revealed a remarkably strong correlation between air pollution levels in New York City and the incidence of arson across the United States. Our research team found a correlation coefficient of 0.8958566, an r-squared value of 0.8025591, and a p-value of less than 0.01. This statistically significant relationship suggests that as air quality in New York City worsens, there is a notable increase in the occurrence of arson incidents nationwide. It's almost as if the polluted air is fanning the flames of criminal activity across the country. Speaking of fanning flames, did you hear about the firefighter who was a great gardener? He really knew how to handle a hose!
The correlation is evident in the scatterplot depicted in Figure 1, which visually illustrates the robust relationship between air pollution levels in New York City and the incidence of arson across the United States. The plot shows a clear upward trend, reinforcing the strength of the association we uncovered. It's as clear as smoke billowing from a chimney on a cold winter's day.
These findings have significant implications for public policy and urban planning efforts, highlighting the need for targeted interventions to mitigate air pollution and address its potential role in fueling arson incidents. As we move forward, it's essential to keep in mind that a breath of fresh air might be just what we need to douse the flames of criminal mischief. After all, who knew that a breath of fresh air could be so crucial in crime prevention? Keep on breathing easy, folks!

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has illuminated a compelling connection between air pollution in New York City and the incidence of arson across the United States. The strikingly strong correlation coefficient of 0.8958566 and p < 0.01 underscore the significance of this relationship, which is as clear as the smoke from a well-tended bonfire. It's almost as if the polluted air is providing the spark for criminal activities nationwide, but fret not, we've got our extinguishers at the ready!

As we look to the future, it's imperative to consider the potential implications of these findings for public policy and urban planning. Perhaps we can say that in addressing air pollution, we're not just clearing the air, but also snuffing out the flames of criminal mischief. After all, who knew that reducing pollution could also reduce crime? It's almost like killing two birds with one stone, but in this case, we're dousing two fires with one hose!

Overall, our study provides valuable insights into the intersection of environmental quality and criminal behavior, reinforcing the need for holistic approaches to address societal challenges. But before we extinguish this topic, let's remember the importance of continued research in understanding the multifaceted influences on criminal activity – after all, there's always room for more "firefighting" in the realm of academia. But for now, let's take a breath of fresh air and savor our findings, because as they say, where there's smoke, there's usually a doctoral thesis!

In summary, we confidently assert that our findings establish a robust relationship between air pollution in the Big Apple and the flare for arson across the nation. With this, we believe no more research is needed in this area – our study has truly set the research world ablaze!


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The Dirty Air Beware: A Flare for Arson in the Big Apple. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Urban Fire Ecology


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Dirty Air Beware: A Flare for Arson in the Big Apple. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Urban Environmental Research and Sustainability


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Dirty Air Beware: A Flare for Arson in the Big Apple with an abstract of In this study, we investigate the potential relationship between air pollution levels in New York City and the incidence of arson across the United States. The findings reveal a strikingly strong correlation between the two, raising eyebrows and flames alike. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our research team discovered a correlation coefficient of 0.8958566 and p < 0.01 for the period spanning 1985 to 2022. This suggests that as the air quality in the bustling urban metropolis deteriorates, so too does the propensity for fiery mischief across the nation. But don't worry, we won't let the pressure burn us out—after all, we'd much prefer to ignite curiosity rather than fires.

ChatGPT:

air pollution, arson, New York City, United States, correlation, Environmental Protection Agency, FBI Criminal Justice Information Services, correlation coefficient, urban metropolis, air quality

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

Air pollution in New York City
Detailed data title: Percentage of days 'unhealthy' or worse air quality in New York-Newark-Jersey City, NY-NJ-PA
Source: Environmental Protection Agency
See what else correlates with Air pollution in New York City

Arson in United States
Detailed data title: The arson rate per 100,000 residents in United States
Source: FBI Criminal Justice Information Services
See what else correlates with Arson in United States

Correlation r = 0.8958566 (Pearson correlation coefficient)
Correlation is a measure of how much the variables move together. If it is 0.99, when one goes up the other goes up. If it is 0.02, the connection is very weak or non-existent. If it is -0.99, then when one goes up the other goes down. If it is 1.00, you probably messed up your correlation function.

r2 = 0.8025591 (Coefficient of determination)
This means 80.3% of the change in the one variable (i.e., Arson in United States) is predictable based on the change in the other (i.e., Air pollution in New York City) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.05E-14. 0.0000000000000304531888068349
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.9 in 3.05E-12% of random cases. Said differently, if you correlated 32,837,283,686,218 random variables You don't actually need 32 trillion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 37 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 37 because we have two variables measured over a period of 38 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.81, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!


All values for the years included above: If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Air pollution in New York City (Bad air quality days)19.452114.520513.698614.20779.5890411.780815.06856.0109311.78089.04118.493158.469948.2191812.602710.68494.918039.5890411.78084.657533.005466.02745.753426.301374.918030.2739733.287672.739731.639340.8219180.5479450.8219180.5464480.5479450.821918000.8219180.273973
Arson in United States (Arson rate)43.646.342.54141.441.74140.837.339.636.734.632.629.728.824.727.726.82523.623.124.422.621.619.518.117.517.614.914.513.714.113.2121113.98.911.6




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Outlandish outliers: There are "outliers" in this data. In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

    For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

    (This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
    They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."


# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([19.4521,14.5205,13.6986,14.2077,9.58904,11.7808,15.0685,6.01093,11.7808,9.0411,8.49315,8.46994,8.21918,12.6027,10.6849,4.91803,9.58904,11.7808,4.65753,3.00546,6.0274,5.75342,6.30137,4.91803,0.273973,3.28767,2.73973,1.63934,0.821918,0.547945,0.821918,0.546448,0.547945,0.821918,0,0,0.821918,0.273973,])
array_2 = np.array([43.6,46.3,42.5,41,41.4,41.7,41,40.8,37.3,39.6,36.7,34.6,32.6,29.7,28.8,24.7,27.7,26.8,25,23.6,23.1,24.4,22.6,21.6,19.5,18.1,17.5,17.6,14.9,14.5,13.7,14.1,13.2,12,11,13.9,8.9,11.6,])
array_1_name = "Air pollution in New York City"
array_2_name = "Arson in United States"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)



Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:


View another random correlation

How fun was this correlation?

Kudos for rating!


Correlation ID: 4057 · Black Variable ID: 20974 · Red Variable ID: 20038
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0